{"id":"W2895106137","doi":"10.48550/arxiv.1810.02334","title":"Unsupervised Learning via Meta-Learning","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":129,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Unsupervised learning; Computer science; Meta learning (computer science); Machine learning; Artificial intelligence; Cluster analysis; Embedding; Construct (python library); Variety (cybernetics); Task (project management); Feature learning; Conceptual clustering; Competitive learning; Fuzzy clustering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008337485,0.0005171688,0.0006531249,0.0004533801,0.0006044344,0.0003712842,0.002191735,0.0003931737,0.0005750448],"category_scores_gemma":[0.0001740031,0.0005762387,0.0005869488,0.0008881105,0.0001705454,0.000598662,0.002469111,0.001883061,0.000933524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001759659,"about_ca_system_score_gemma":0.0001927754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001125606,"about_ca_topic_score_gemma":0.00001322263,"domain_scores_codex":[0.9964694,0.0007802878,0.0003289299,0.001593788,0.0002228405,0.0006047269],"domain_scores_gemma":[0.997603,0.0002415814,0.0004658612,0.001060103,0.0003204869,0.0003089798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003713812,0.00008568562,0.002863449,0.00008637205,0.00123409,0.00038009,0.00170467,0.9375481,0.0001384607,0.05165483,0.0002724748,0.003994626],"study_design_scores_gemma":[0.0005189726,0.0001197014,0.0007510804,0.00004272187,0.0004503199,0.000009052157,0.0002025123,0.9673602,0.00007739207,0.009489679,0.02023637,0.0007420238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04062368,0.0001621018,0.9427909,0.0001257509,0.0006242599,0.0002360811,0.000001330859,0.0009819444,0.01445397],"genre_scores_gemma":[0.9799616,0.0001213853,0.007941877,0.0001852218,0.000148366,0.000002199999,0.00002511784,0.00004511256,0.01156912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9393379,"threshold_uncertainty_score":0.9998444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1250216964980959,"score_gpt":0.1969916416368858,"score_spread":0.0719699451387899,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}